© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 30623
    Prev
    Next
    INDEX
    Explanations

    words related to specific biological or medical sampling and analysis

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    oyan
    -0.77
    ```
    -0.71
    coran
    -0.70
    BeginContext
    -0.69
    Ссылки
    -0.68
     Ehren
    -0.68
    BERG
    -0.67
     Boga
    -0.67
     phố
    -0.66
    edia
    -0.65
    POSITIVE LOGITS
     Saar
    1.28
     sails
    1.14
    Sa
    1.13
     SAIL
    1.13
     Sadie
    1.11
     SA
    1.08
     Saul
    1.08
     Sait
    1.05
     Sa
    1.01
     Saif
    1.00
    Activations Density 0.049%

    No Known Activations